Under CopyrightGourishetti, SaichandSaichandGourishettiChauhan, JaydeepJaydeepChauhanGrollmisch, SaschaSaschaGrollmischRohe, MaximilianMaximilianRoheSennewald, MartinMartinSennewaldHildebrand, JörgJörgHildebrandBergmann, Jean PierreJean PierreBergmann2023-06-142024-02-292023-06-142023https://doi.org/10.24406/publica-1463https://publica.fraunhofer.de/handle/publica/44278310.5162/SMSI2023/D7.210.24406/publica-1463This paper investigates the potential of airborne sound analysis in the human hearing range for automatic defect classification in the arc welding process. We propose a novel sensor setup using microphones and perform several recording sessions under different process conditions. The proposed quality monitoring method using convolutional neural networks achieves 80.5% accuracy in detecting deviations in the arc welding process. This confirms the suitability of airborne analysis and leaves room for improvement in future work.enweldingAImachine-learningprocess monitoringAnalyse Industriegeräuscheconference paper